初始化项目,由ModelHub XC社区提供模型

Model: Kunhao/pile-7b-250b-tokens
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 10:04:58 +08:00
commit 1ae963e5f5
12 changed files with 147424 additions and 0 deletions

13
tokenizer_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"add_prefix_space": false,
"additional_special_tokens": [
"<|endoftext|>"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}